Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1405 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0003

Data Index: 870679 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0770. Min Act: -0.0003

Data Index: 800026 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0753. Min Act: -0.0003

Data Index: 1091140 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0753. Min Act: -0.0003

Data Index: 709309 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0739. Min Act: -0.0003

Data Index: 489397 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0749. Min Act: -0.0003

Data Index: 280602 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0735. Min Act: -0.0003

Data Index: 629850 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0732. Min Act: -0.0004

Data Index: 783274 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0712. Min Act: -0.0003

Data Index: 1258285 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0705. Min Act: -0.0003

Data Index: 654674 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0716. Min Act: -0.0004

Data Index: 423600 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0715. Min Act: -0.0004

Data Index: 149044 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0734. Min Act: -0.0003

Data Index: 758734 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0727. Min Act: -0.0003

Data Index: 1244039 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0721. Min Act: -0.0003

Data Index: 585943 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0686. Min Act: -0.0003

Data Index: 1058937 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0711. Min Act: -0.0003

Data Index: 1289827 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0683. Min Act: -0.0004

Data Index: 831159 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0715. Min Act: -0.0003

Data Index: 119875 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0705. Min Act: -0.0003

Data Index: 17968 (C4 (Web Text))

Max Activating Token Index: 681